Meta-learning as a principle for human-like visual representations

• URL: http://arxiv.org/abs/2606.28399v1
• Date: Wed, 24 Jun 2026 09:28:17 GMT
• Title: Meta-learning as a principle for human-like visual representations
• Abstract summary: Pretrained neural networks model human visual representations with unprecedented success.<n>We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks.<n>We train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts.<n>Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex.
• Score: 22.433335919496717
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented success, a large discrepancy remains. We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks. We hypothesise this flexibility arises from meta-learning (learning to learn), a pressure shaping representations to acquire new tasks from few observations. To test this, we train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts. Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex. Behavioural gains depend on disentangled, high-level task distributions, while brain alignment is driven primarily by the learning-to-learn pressure. Our results suggest the flexibility of human visual representations reflects the functional demand to learn new semantic relationships on the fly.

Related papers

• An extremely coarse feedback signal is sufficient for learning human-aligned visual representations [2.9506547907696006]
  We investigate how the coarseness of a learning signal shapes representational alignment with human vision.<n>We train hundreds of neural networks across convolutional and transformer architectures on these coarse classification tasks.<n>We find that networks trained to distinguish as few as 8 broad categories learn representations that match or exceed the neural alignment of models distinguishing 1,000-classes.
  arXiv  Detail & Related papers  (2026-05-07T01:02:21Z)
• Human-level 3D shape perception emerges from multi-view learning [63.048728487674815]
  We develop a modeling framework that predicts human 3D shape inferences for arbitrary objects.<n>We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data.<n>We find that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data.
  arXiv  Detail & Related papers  (2026-02-19T18:56:05Z)
• Revealing emergent human-like conceptual representations from language prediction [90.73285317321312]
  Large language models (LLMs) trained solely through next-token prediction on text exhibit strikingly human-like behaviors.<n>Are these models developing concepts akin to those of humans?<n>We found that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts.
  arXiv  Detail & Related papers  (2025-01-21T23:54:17Z)
• Aligning Machine and Human Visual Representations across Abstraction Levels [31.78285373363057]
  Deep neural networks have achieved success across a wide range of applications, including as models of human behavior and neural representations in vision tasks.<n>However, neural network training and human learning differ in fundamental ways, and neural networks often fail to generalize as robustly as humans do raising questions regarding the similarity of their underlying representations.<n>We highlight a key misalignment between vision models and humans: whereas human conceptual knowledge is hierarchically organized from fine- to coarse-scale distinctions, model representations do not accurately capture all these levels of abstraction.<n>To address this misalignment, we first train a teacher model to imitate human judgments, then transfer human-aligned
  arXiv  Detail & Related papers  (2024-09-10T13:41:08Z)
• What Makes Pre-Trained Visual Representations Successful for Robust Manipulation? [57.92924256181857]
  We find that visual representations designed for manipulation and control tasks do not necessarily generalize under subtle changes in lighting and scene texture. We find that emergent segmentation ability is a strong predictor of out-of-distribution generalization among ViT models.
  arXiv  Detail & Related papers  (2023-11-03T18:09:08Z)
• Visual Grounding Helps Learn Word Meanings in Low-Data Regimes [47.7950860342515]
  Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension. But to achieve these results, LMs must be trained in distinctly un-human-like ways. Do models trained more naturalistically -- with grounded supervision -- exhibit more humanlike language learning? We investigate this question in the context of word learning, a key sub-task in language acquisition.
  arXiv  Detail & Related papers  (2023-10-20T03:33:36Z)
• Human-oriented Representation Learning for Robotic Manipulation [64.59499047836637]
  Humans inherently possess generalizable visual representations that empower them to efficiently explore and interact with the environments in manipulation tasks. We formalize this idea through the lens of human-oriented multi-task fine-tuning on top of pre-trained visual encoders. Our Task Fusion Decoder consistently improves the representation of three state-of-the-art visual encoders for downstream manipulation policy-learning.
  arXiv  Detail & Related papers  (2023-10-04T17:59:38Z)
• Seeing in Words: Learning to Classify through Language Bottlenecks [59.97827889540685]
  Humans can explain their predictions using succinct and intuitive descriptions. We show that a vision model whose feature representations are text can effectively classify ImageNet images.
  arXiv  Detail & Related papers  (2023-06-29T00:24:42Z)
• Evaluating alignment between humans and neural network representations in image-based learning tasks [5.657101730705275]
  We tested how well the representations of $86$ pretrained neural network models mapped to human learning trajectories.<n>We found that while training dataset size was a core determinant of alignment with human choices, contrastive training with multi-modal data (text and imagery) was a common feature of currently publicly available models that predicted human generalisation.<n>In conclusion, pretrained neural networks can serve to extract representations for cognitive models, as they appear to capture some fundamental aspects of cognition that are transferable across tasks.
  arXiv  Detail & Related papers  (2023-06-15T08:18:29Z)
• Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models [57.08925810659545]
  We conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models. Our empirical observations suggest that vision-and-language models are better at label prediction tasks. We hope our study sheds light on the role of language in visual learning, and serves as an empirical guide for various pretrained models.
  arXiv  Detail & Related papers  (2022-12-01T05:00:18Z)
• Human alignment of neural network representations [28.32452075196472]
  We investigate the factors that affect the alignment between the representations learned by neural networks and human mental representations inferred from behavioral responses.<n>We find that model scale and architecture have essentially no effect on the alignment with human behavioral responses.<n>We find that some human concepts such as food and animals are well-represented by neural networks whereas others such as royal or sports-related objects are not.
  arXiv  Detail & Related papers  (2022-11-02T15:23:16Z)
• Human-Understandable Decision Making for Visual Recognition [30.30163407674527]
  We propose a new framework to train a deep neural network by incorporating the prior of human perception into the model learning process. The effectiveness of our proposed model is evaluated on two classical visual recognition tasks.
  arXiv  Detail & Related papers  (2021-03-05T02:07:33Z)
• What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions [50.435861435121915]
  We use human interaction and attention cues to investigate whether we can learn better representations compared to visual-only representations. Our experiments show that our "muscly-supervised" representation outperforms a visual-only state-of-the-art method MoCo.
  arXiv  Detail & Related papers  (2020-10-16T17:46:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.